Use `regex` instead of `re`

spacy/fr/tokenizer_exceptions.py

@@ -13,7 +13,7 @@ from ..symbols import *
 
 import os
 import io
-import re
+import regex as re
 
 
 def get_exceptions():

spacy/hu/tokenizer_exceptions.py

@@ -1,7 +1,7 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-import re
+import regex as re
 
 from spacy.language_data.punctuation import ALPHA_LOWER, CURRENCY
 from ..language_data.tokenizer_exceptions import _URL_PATTERN

spacy/language_data/punctuation.py

@@ -16,6 +16,8 @@ A Ä À Á Â Ǎ Æ Ã Å Ā Ă Ą B C Ç Ć Č Ĉ Ċ C̄ D Ð Ď E É È Ê Ë
 Î Ï Í Ī Ì Ȉ Ǐ Į Ĩ J K Ķ L Ł Ļ M N Ñ Ń Ň Ņ O Ö Ó Ò Ő Ô Õ Œ Ø Ō Ő Ǒ Ơ P Q R Ř Ŗ S
 Ś Š Ş Ŝ T Ť U Ú Û Ù Ú Ū Ű Ǔ Ů Ų Ư V W Ŵ X Y Ÿ Ý Ỳ Ŷ Ỹ Z Ź Ž Ż Þ
 """
+import regex as re
+re.DEFAULT_VERSION = re.VERSION1
 
 
 _UNITS = """

spacy/util.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals, print_function
 
 import ujson
-import re
+import regex as re
 from pathlib import Path
 import sys
 import textwrap